© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 194621
    Prev
    Next
    INDEX
    Explanations

    dog breeds

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Tez
    0.40
    judice
    0.39
     Cinematic
    0.38
    achery
    0.38
     Por
    0.37
     Pacific
    0.37
    Blue
    0.37
     Bloss
    0.37
    爨
    0.37
    sth
    0.36
    POSITIVE LOGITS
     mast
    0.75
    Mast
    0.71
     Mast
    0.68
    mast
    0.62
     Newfoundland
    0.59
     MAST
    0.56
    Leon
    0.54
    Rot
    0.53
     masts
    0.52
     sheep
    0.51
    Activations Density 0.002%

    No Known Activations